Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly=false, idempotent=true, destructive=true; the description adds cost and authorization behavior (administrator-configured model, per-image price, default 2 credits), spending-policy vs approval semantics, and the fact that 'running' means background analysis where the agent should wait and follow nextAction to retrieve a free receipt without restarting. That is substantial behavior beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then the cost/approval model, then the workflow and the sibling redirect. Dense and information-rich, though the middle sentences are packed close together and would read better as separated clauses.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-action paid tool with an output schema, the description covers pricing, approval, resumption, and the background-running state machine — including the nextAction follow-up — so nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning: auto/run/get accept only the original requestId, and requestId reuse avoids a new analysis. The action enum's intent is reinforced rather than merely repeated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — reconstructing Chinese/English generation prompts, negative terms and visual anchors from one image — which is unambiguous and clearly distinct from sibling tools like generate_image or derive_image. It also explicitly marks its boundary against generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives per-action guidance (preview freezes and quotes, auto obeys spending policy, run needs explicit approval, get resumes a receipt for free) and states an exclusion plus alternative: 'No automatic image generation; use generate_image with a separate quote to validate.' An agent knows both when to use each action and when to route elsewhere.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.